Results 71 to 80 of about 505,656 (201)

Adversarial Attacks on Human Vision

CoRR, 2022
This article presents an introduction to visual attention retargeting, its connection to visual saliency, the challenges associated with it, and ideas for how it can be approached. The difficulty of attention retargeting as a saliency inversion problem lies in the lack of one-to-one mapping between saliency and the image domain, in addition to the ...
Victor A. Mateescu, Ivan V. Bajic
openaire   +2 more sources

Real-Time Adversarial Attacks [PDF]

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019
In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are very effective, they only focus on scenarios where the target model takes static input, i.e., an attacker can ...
Yuan Gong 0001, Boyang Li 0003, Christian Poellabauer, Yiyu Shi 0001   +3 more
openaire   +4 more sources

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack

CoRR
In recent times, the swift evolution of adversarial attacks has captured widespread attention, particularly concerning their transferability and other performance attributes. These techniques are primarily executed at the sample level, frequently overlooking the intrinsic parameters of models.
Zhibo Jin, Jiayu Zhang 0001, Zhiyu Zhu, Chenyu Zhang, Jiahao Huang, Jianlong Zhou, Fang Chen 0001   +6 more
openaire   +2 more sources

Boosting Adversarial Attacks with Momentum [PDF]

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018
Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences. Adversarial attacks serve as an important surrogate to evaluate the robustness of deep learning models before they are deployed.
Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su 0006, Jun Zhu 0001, Xiaolin Hu 0001, Jianguo Li   +6 more
openaire   +2 more sources

Adversarial Attack’s Impact on Machine Learning Model in Cyber-Physical Systems

, 2020
Deficiency of correctly implemented and robust defence leaves Internet of Things devices vulnerable to cyber threats, such as adversarial attacks. A perpetrator can utilize adversarial examples when attacking Machine Learning models used in a cloud data ...
Vähäkainu, Petri, Lehto, Martti, Kariluoto, Antti   +2 more
core   +1 more source

Adversarial Risk Analysis: The Somali Pirates case [PDF]

, 2013
Some of the current world’s biggest problems revolve around security issues. This has raised recent interest in resource allocation models to manage security threats, from terrorism to organized crime through money laundering.
Ríos, Jesús, Ríos Insúa, David
core  

Review of Research on Adversarial Attack in Three Kinds of Images [PDF]

Jisuanji kexue yu tansuo
In recent years, there have been numerous breakthroughs in deep learning, leading to the expansion of applications based on deep learning into a wide range of fields.
XU Yuhui, PAN Zhisong, XU Kun
doaj   +1 more source

Object-Attentional Untargeted Adversarial Attack

, 2022
Deep neural networks are facing severe threats from adversarial attacks. Most existing black-box attacks fool target model by generating either global perturbations or local patches.
Wang, Yuan-Gen, Zhou, Chao, Zhu, Guopu
core  

SURVEY OF ADVERSARIAL ATTACKS AND DEFENSE AGAINST ADVERSARIAL ATTACKS

Darpan International Research Analysis
In recent years, the fields of Artificial Intelligence (AI) and Deep learning (DL) techniques along with Neural Networks (NNs) have shown great progress and scope for future research. Along with all the developments comes the threats and security vulnerabilities to Neural Networks and AI models. A few fabricated inputs/samples can lead to deviations in
Akshat Jain, Sanskar Agarwal, Armaan Pareek, Vanshika Singh   +3 more
openaire   +1 more source

Harmonic Adversarial Attack Method

CoRR, 2018
Adversarial attacks find perturbations that can fool models into misclassifying images. Previous works had successes in generating noisy/edge-rich adversarial perturbations, at the cost of degradation of image quality. Such perturbations, even when they are small in scale, are usually easily spottable by human vision.
Wen Heng, Shuchang Zhou 0001, Tingting Jiang 0001   +2 more
openaire   +2 more sources